© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 8-RES_POST_32K-OAI
    11. 6194
    Prev
    Next
    INDEX
    Explanations

    specific types of names or terms related to categories or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    standard
    Context Size
    64
    Dataset
    Skylion007/openwebtext
    Activation Function
    topk
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    362
    +0.11
    0.5%
    496
    +0.10
    0.5%
    412
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    42
    +0.11
    0.01
    406
    +0.10
    0.01
    687
    +0.09
    0.01
    Negative Logits
    zsche
    -0.81
    sembly
    -0.78
    hesis
    -0.77
    ggle
    -0.74
     Flavoring
    -0.74
    utics
    -0.72
    seys
    -0.71
    rity
    -0.71
    azor
    -0.71
    heses
    -0.70
    POSITIVE LOGITS
    çĶ°
    1.20
    æĸ¹
    1.02
    è
    1.01
    é¾į
    0.96
    ãĤ´ãĥ³
    0.96
    ç
    0.93
    æľ
    0.89
    æĺ
    0.89
    é»Ĵ
    0.86
    ãĤĬ
    0.85
    Activations Density 0.010%

    No Known Activations